INDEX

Explanations

phrases related to public opinion and media narratives surrounding various topics

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GEBURTSDATUM

-0.81

 AssemblyCulture

-0.72

UnusedPrivate

-0.71

LLocation

-0.66

IsMutable

-0.64

COLLE

-0.61

 pleaſure

-0.60

 kaarangay

-0.57

الحياه

-0.57

PreferredItem

-0.56

POSITIVE LOGITS

 hype

1.42

 hyped

1.18

 touted

1.11

 fanfare

1.09

hype

1.03

 talk

1.02

 fuss

1.00

 publicized

1.00

 publicity

1.00

 media

0.93

Activations Density 0.434%

phrases related to public opinion and media narratives surrounding various topics

No Comments

No Known Activations